Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    probability and elasticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     тяж
    1.25
     draped
    1.18
     assertThat
    1.14
     adorned
    1.13
     fragrances
    1.12
     escorted
    1.12
     toasted
    1.11
    注意到
    1.11
     GAO
    1.11
    満
    1.10
    POSITIVE LOGITS
    ding
    1.02
    ം
    1.01
    ING
    0.99
    ^{-\
    0.98
    ńska
    0.97
    xer
    0.95
    งาน
    0.94
    }^{-\
    0.93
    ils
    0.93
    షల్
    0.93
    Act Density 0.000%

    No Known Activations